Hugging Face's logo

SiMajid
/
llm_blender_value_v4

Transformers
Safetensors
roberta
Model card Files
xet
 Community
SiMajid commited on
Commit
23f56d8
·
1 Parent(s): f68dc6d

Initial commit with checkpoint files

Browse files
Files changed (9) hide show
  1. added_tokens.json +6 -0
  2. config.json +20 -0
  3. merges.txt +0 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +15 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +89 -0
  8. training_args.bin +3 -0
  9. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<|candidate1|>": 50266,
3
+ "<|candidate2|>": 50267,
4
+ "<|candidate|>": 50268,
5
+ "<|source|>": 50265
6
+ }
config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "ranker_type": "pairranker",
3
+ "model_type": "roberta",
4
+ "model_name": "roberta-large",
5
+ "cache_dir": "./hf_models/roberta-large/",
6
+ "load_checkpoint": null,
7
+ "source_maxlength": 128,
8
+ "candidate_maxlength": 128,
9
+ "n_tasks": 1,
10
+ "num_pos": 5,
11
+ "num_neg": 5,
12
+ "sub_sampling_mode": "all_pair",
13
+ "sub_sampling_ratio": 0.4,
14
+ "loss_type": "instructgpt",
15
+ "reduce_type": "linear",
16
+ "inference_mode": "bubble",
17
+ "drop_out": 0.05,
18
+ "fp16": true,
19
+ "device": null
20
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff0e77994dd2573d20628734406bf314926c6d8a0234fb763e327861cb5616d2
3
+ size 714977746
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50265": {
45
+ "content": "<|source|>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50266": {
53
+ "content": "<|candidate1|>",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50267": {
61
+ "content": "<|candidate2|>",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50268": {
69
+ "content": "<|candidate|>",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ }
76
+ },
77
+ "bos_token": "<s>",
78
+ "clean_up_tokenization_spaces": true,
79
+ "cls_token": "<s>",
80
+ "eos_token": "</s>",
81
+ "errors": "replace",
82
+ "mask_token": "<mask>",
83
+ "model_max_length": 512,
84
+ "pad_token": "<pad>",
85
+ "sep_token": "</s>",
86
+ "tokenizer_class": "RobertaTokenizer",
87
+ "trim_offsets": true,
88
+ "unk_token": "<unk>"
89
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:101589ea6d84285e594f590fc23d07dd1fabac4237ce866752b45731bc1e1cf4
3
+ size 6840
vocab.json ADDED
The diff for this file is too large to render. See raw diff